Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add fabric-testbed/claude-plugin-marketplace --skill fabric-helpgit clone --depth 1 https://github.com/fabric-testbed/claude-plugin-marketplaceWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/fabric-testbed/claude-plugin-marketplace/fabric-help)<a href="https://agentmods.dev/skills/fabric-testbed/claude-plugin-marketplace/fabric-help"><img src="https://agentmods.dev/badge/skills/fabric-testbed/claude-plugin-marketplace/fabric-help/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fabric-testbed/claude-plugin-marketplace/fabric-help"><img src="https://agentmods.dev/badge/skills/fabric-testbed/claude-plugin-marketplace/fabric-help.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00015 | $0.00762 |
| Opus 5.5 | $0.00006 | $0.00305 |
| Sonnet 5.5 | $0.00003 | $0.00152 |
| Haiku 4.5 | $0.00002 | $0.00076 |
Grade A, and why
fabric-help scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FABRIC Testbed Toolkit — Navigation
You are a FABRIC testbed experiment assistant. The user has invoked /fabric-help.
Display the following navigation table so the user knows which skill to use:
Available Skills
Setup & Discovery
| Skill | When to Use | What It Does |
|---|---|---|
/fabric-configure |
Setting up FABRIC environment | Generates setup code: FablibManager init, SSH keys, token config, validation |
/fabric-resources |
Finding available resources | Queries sites, hardware, images, capacity with filter functions |
Slice Lifecycle
| Skill | When to Use | What It Does |
|---|---|---|
/fabric-slice-create |
Creating a new experiment | Generates code to create slices with nodes, components, and networks |
/fabric-slice-manage |
Managing existing experiments | List, inspect, renew, modify, and delete slices |
Networking
| Skill | When to Use | What It Does |
|---|---|---|
/fabric-network |
Configuring networking | L2/L3 networks, FABnet, public IPs, VLANs, facility ports |
/fabric-routing |
Routing and tunneling | Static routes, WireGuard VPN, sshuttle, performance tuning |
/fabric-vpn |
VPN and remote access | Tailscale mesh VPN, SSH tunnels for accessing services |
/fabric-facility-ports |
Inter-testbed connections | Connect to Chameleon/CloudLab, port mirroring |
/fabric-programmable-networking |
Programmable data planes | P4 Tofino switches, DPDK SmartNICs, BlueField DPUs, OVS |
Hardware & Components
| Skill | When to Use | What It Does |
|---|---|---|
/fabric-gpu |
Provisioning GPUs | GPU node creation with NVIDIA driver and CUDA installation |
/fabric-storage |
Configuring storage | NVMe, persistent storage, local disk setup |
/fabric-fpga |
FPGA experiments | Xilinx U280 provisioning, ESnet/NEU/XDMA bitstream flashing |
/fabric-containers |
Container workloads | Docker deployment, Kubernetes clusters |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 76 lines · 15 tokens per session scan A 01d1ec5c838b
fabric-help is a skill published in the GitHub repository fabric-testbed/claude-plugin-marketplace (2 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 762 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
fabric-help compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fabric-helpfabric-testbed/claude-plugin-marketplace | Skill | 2 | 8mo ago | Apache-2.0 | A | 15 | Claude Code |
| neuroskill-bciNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 18 | Claude Code, Codex |
| ruview-applicationsruvnet/RuView | Skill | 103k | yesterday | MIT | A | 79 | Claude Code |
| lab-hardware-cadK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 108 | Claude Code |
| pylabrobotK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 49 | Claude Code |
| pybammK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 70 | Claude Code, Codex |
| calibrate-roomruvnet/RuView | Skill | 103k | yesterday | MIT | A | 41 | Claude Code |